Regional Inference

Regional inference routes your API requests to models hosted in a specific geographic region, guaranteeing that inference occurs within that region and processed data never leaves it. If you don't specify a region, the API uses the global Mistral endpoint.

Use a regional endpoint when your application needs requests processed in a specific geographic region. Each region group maps to a dedicated base URL and can include several data centers in that geography.

Use the server parameter when initializing the client to specify the region:

import os
from mistralai.client import Mistral

client = Mistral(api_key=os.environ["MISTRAL_API_KEY"], server="eu")
response = client.chat.complete(
    model="mistral-medium-latest",
    messages=[{"role": "user", "content": "What is Mistral AI?"}],
)
print(response.choices[0].message.content)

import os
from mistralai.client import Mistral

client = Mistral(api_key=os.environ["MISTRAL_API_KEY"], server="eu")
response = client.chat.complete(
    model="mistral-medium-latest",
    messages=[{"role": "user", "content": "What is Mistral AI?"}],
)
print(response.choices[0].message.content)

If using an older SDK, use the server_url parameter instead:

from mistralai.client import Mistral

client = Mistral(api_key=os.environ["MISTRAL_API_KEY"], server_url="https://api.eu.mistral.ai/")
list_models_response = client.models.list()
print(list_models_response)

from mistralai.client import Mistral

client = Mistral(api_key=os.environ["MISTRAL_API_KEY"], server_url="https://api.eu.mistral.ai/")
list_models_response = client.models.list()
print(list_models_response)

curl https://api.eu.mistral.ai/v1/chat/completions \
  -H "Authorization: Bearer $MISTRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral-large-latest",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

curl https://api.eu.mistral.ai/v1/chat/completions \
  -H "Authorization: Bearer $MISTRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral-large-latest",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

Regional endpoints only serve models hosted in that region. Use models.list against the regional base URL to see which models are available.

import os
from mistralai.client import Mistral

client = Mistral(api_key=os.environ["MISTRAL_API_KEY"], server="eu")
models = client.models.list()
for model in models.data:
    print(model.id)

import os
from mistralai.client import Mistral

client = Mistral(api_key=os.environ["MISTRAL_API_KEY"], server="eu")
models = client.models.list()
for model in models.data:
    print(model.id)

Regional inference is billed at 1.1× standard list pricing (a 10% upcharge) for input tokens, output tokens, cached reads, and cache writes.

• Not all Tool calls are currently supported. Function Calling is the only supported regional tool.
• Stateful features (Agents, Batch, Files API) are not available on regional endpoints.
• Available models vary by region.